© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 13356
    Prev
    Next
    INDEX
    Explanations

    words related to a specific proper noun, "Sauk" or potentially "Sauk Tribe"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Zahi."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tact
    -0.75
     Rust
    -0.68
    sold
    -0.67
     tact
    -0.66
    able
    -0.66
     stud
    -0.63
     conj
    -0.63
    rend
    -0.62
     VP
    -0.62
     count
    -0.61
    POSITIVE LOGITS
    ahi
    4.93
    aha
    1.14
    ahar
    1.02
    hai
    1.01
    aho
    1.01
    interstitial
    0.99
    ahon
    0.99
    hani
    0.99
    ahu
    0.98
    uay
    0.94
    Activations Density 0.018%

    No Known Activations